BROCODE Summary Statistics

Final Project Summary Statistics

# Always print this out before your assignment
sessionInfo()

R version 4.1.1 (2021-08-10)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 18363)

Matrix products: default

locale:
[1] LC_COLLATE=English_United States.1252  LC_CTYPE=English_United States.1252   
[3] LC_MONETARY=English_United States.1252 LC_NUMERIC=C                          
[5] LC_TIME=English_United States.1252    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] sjmisc_2.8.7                 janitor_2.1.0                randomForestExplainer_0.10.1
 [4] randomForest_4.6-14          titanic_0.1.0                viridis_0.6.2               
 [7] viridisLite_0.4.0            pastecs_1.3.21               kableExtra_1.3.4            
[10] lubridate_1.7.10             rsample_0.1.0                ggthemes_4.2.4              
[13] ggrepel_0.9.1                here_1.0.1                   fs_1.5.0                    
[16] forcats_0.5.1                stringr_1.4.0                dplyr_1.0.7                 
[19] purrr_0.3.4                  readr_2.0.1                  tidyr_1.1.3                 
[22] tibble_3.1.4                 ggplot2_3.3.5                tidyverse_1.3.1             
[25] knitr_1.34                   RSQLite_2.2.8               

loaded via a namespace (and not attached):
 [1] bit64_4.0.5        insight_0.14.4     RColorBrewer_1.1-2 webshot_0.5.2      httr_1.4.2        
 [6] rprojroot_2.0.2    tools_4.1.1        backports_1.2.1    sjlabelled_1.1.8   DT_0.19           
[11] utf8_1.2.2         R6_2.5.1           DBI_1.1.1          colorspace_2.0-2   withr_2.4.2       
[16] GGally_2.1.2       tidyselect_1.1.1   gridExtra_2.3      bit_4.0.4          compiler_4.1.1    
[21] cli_3.0.1          rvest_1.0.1        pacman_0.5.1       xml2_1.3.2         labeling_0.4.2    
[26] pdp_0.7.0          scales_1.1.1       systemfonts_1.0.3  digest_0.6.27      rmarkdown_2.11    
[31] svglite_2.0.0      pkgconfig_2.0.3    htmltools_0.5.2    parallelly_1.28.1  DALEX_2.3.0       
[36] dbplyr_2.1.1       fastmap_1.1.0      htmlwidgets_1.5.4  rlang_0.4.11       readxl_1.3.1      
[41] rstudioapi_0.13    farver_2.1.0       visNetwork_2.1.0   generics_0.1.0     jsonlite_1.7.2    
[46] magrittr_2.0.1     Rcpp_1.0.7         munsell_0.5.0      fansi_0.5.0        lifecycle_1.0.0   
[51] furrr_0.2.3        stringi_1.7.4      yaml_2.2.1         snakecase_0.11.0   plyr_1.8.6        
[56] grid_4.1.1         blob_1.2.2         parallel_4.1.1     listenv_0.8.0      crayon_1.4.1      
[61] lattice_0.20-44    haven_2.4.3        hms_1.1.0          pillar_1.6.2       boot_1.3-28       
[66] codetools_0.2-18   reprex_2.0.1       glue_1.4.2         evaluate_0.14      data.table_1.14.0 
[71] modelr_0.1.8       vctrs_0.3.8        tzdb_0.1.2         cellranger_1.1.0   gtable_0.3.0      
[76] reshape_0.8.8      future_1.22.1      assertthat_0.2.1   cachem_1.0.6       xfun_0.26         
[81] broom_0.7.9        memoise_2.0.0      globals_0.14.0     ellipsis_0.3.2    

getwd()

[1] "C:/BUS_696/final_project/BROCODE_Final_Project"

# load all your libraries in this chunk 
library('tidyverse')
library("fs")
library('here')
library('dplyr')
library('tidyverse')
library('ggplot2')
library('ggrepel')
library('ggthemes')
library('forcats')
library('rsample')
library('lubridate')
library('ggthemes')
library('kableExtra')
library('pastecs')
library('viridis')


# note, do not run install.packages() inside a code chunk. install them in the console outside of a code chunk. 

Final Project Cleaning and Summary Statistics

1a) Loading data

#Reading the data in and doing minor initial cleaning in the function call
#Reproducible data analysis should avoid all automatic string to factor conversions.
#strip.white removes white space 
#na.strings is a substitution so all that have "" will = na
data <- read.csv(here::here("final_project", "donor_data.csv"),
                 stringsAsFactors = FALSE,
                 strip.white = TRUE,
                 na.strings = "")

1b) Fixing the wonky DOB & Data cleanup

1c Creating factor variable for sex

datacleaning <- 
  datacleaning %>% 
  mutate(sex_fct = 
           fct_explicit_na(Sex)
  )


datacleaning <-
datacleaning %>% 
mutate(
  sex_simple = 
    fct_lump_n(Sex, n = 4)
)

#checking to see if its a factor
class(datacleaning$sex_fct)

[1] "factor"

#checking levels
levels(datacleaning$sex_simple)

[1] "F" "M" "U" "X"

#creating a table against Sex column 
table(datacleaning$sex_fct, datacleaning$sex_simple)

           
                 F      M      U      X
  F         120857      0      0      0
  M              0 108322      0      0
  U              0      0   3684      0
  X              0      0      0      7
  (Missing)      0      0      0      0

1d #Mean, Median, and Count of Giving in Age Ranges

age_range_giving <- datacleaning %>%
  group_by(age_range) %>%
  summarise(avg_giving = mean(HH.Lifetime.Giving, na.rm = TRUE),
            med_giving = median(HH.Lifetime.Giving, na.rm = TRUE),
            amount_of_people_in_age_range = n())

Question 2

2a) Plotting average giving by age range

ggplot(age_range_giving, aes(avg_giving, age_range)) +
  geom_bar(stat = "identity")

NA
NA

2b) Count of donors based on age range (another way to look at it)

ggplot(datacleaning, 
       aes(age_range)) + 
       geom_bar() + 
       theme(axis.text.x = element_text(angle=45,
                                        hjust=1)) + 
  labs(title = "Count of Age Ranges", x = "", y = "")
  

2c) Boxplot of the Age Ranges Against the Lifetime Giving Amounts with a log scale applied - the reason we applied log scale is to resolve issues with visualizations that skew towards large values in our dataset.

ggplot(datacleaning, aes(age_range,HH.Lifetime.Giving,fill = age_range)) + 
  geom_boxplot(
  outlier.colour = "red") + 
  scale_y_log10() +
  theme(axis.text.x=element_text(angle=45,hjust=1))
  

2d) Splitting by age and gender

#creating boxplots 
datacleaning %>% 
  filter(Age < 100) %>% #removing the weird outliers that are over 100 
  filter(Sex %in% c("M", "F")) %>%
  ggplot(aes(Sex, Age)) + 
  geom_boxplot() + 
  theme_economist() + 
  ggtitle("Ages of Donors Based on Gender") + 
  xlab(NULL) + ylab(NULL)
  
  
  

2e) Distribution of people in the states that they live.

  datacleaning %>%
  mutate(State = ifelse(State == " ", "NA", State)) %>%
  filter(State != "NA") %>%
  group_by(State) %>%
  summarise(Count = length(State)) %>%
  filter(Count > 800) %>%
  arrange(-Count) %>%
  kable(col.names = c("Donor's State", "Count")) %>%
  kable_styling(bootstrap_options = c("condensed"),
                full_width = F)
  
 
  
  

2f) Looking at all donors first gift amount. 75% made a first gift of <100.

 no_non_donors <- datacleaning %>%
  filter(Lifetime.Giving != 0)
  
nd <- quantile(no_non_donors$HH.First.Gift.Amount, probs = c(.25,.50,.75,.9,.99), na.rm = TRUE)

nd <- as.data.frame(nd)

nd %>%
  kable(col.names = "Quantile") %>%
  kable_styling(bootstrap_options = c("striped", "hover"),
                full_width = F)
  
  

Modeling for you

3a) Linear model

#converting married Y and N to 1 and 0 
datacleaning <- datacleaning %>%
      mutate(Married_simple = ifelse(Married == "N",0,1))
 

mod1lm <- lm( Married ~ Lifetime.Giving,
           data = datacleaning)

Error in lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) : 
  NA/NaN/Inf in 'y'

3a)

p <- datacleaning %>%
  ggplot(aes(Age)) + geom_histogram(bins=30, fill = "blue") + theme_economist_white() +
  ggtitle("Overall Donor Age Distribution") + 
  xlab(NULL) + ylab(NULL) + scale_x_continuous(breaks = seq(5,100,by = 20)) +
  scale_y_continuous(breaks = seq(20,100,by = 20)) + xlim(c(20,100))

Scale for 'x' is already present. Adding another scale for 'x', which will replace the existing
scale.

ggplotly(p)

  
p

ggplot(data = datacleaning, aes(x = Age)) + geom_histogram(fill ="blue")+ xlim(c(20,100))

`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

NA
NA
NA